Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    document metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聯絡
    -0.06
    宋
    -0.06
    (bb
    -0.06
     costs
    -0.06
    פיתוח
    -0.06
     suits
    -0.06
    扈
    -0.06
    AMILY
    -0.06
    /Table
    -0.06
    ISOString
    -0.06
    POSITIVE LOGITS
    eks
    0.07
     Bates
    0.07
    -animate
    0.07
     sayısı
    0.07
    bern
    0.06
    有关规定
    0.06
    信じ
    0.06
     Aware
    0.06
     Recommended
    0.06
     Regel
    0.06
    Act Density 0.005%

    No Known Activations